Get the latest tech news

Deep Learning Is Applied Topology

Everything lives on a manifold

We may not be able to define 'good' and 'bad' in strict mathematical terms, but as long as we can separate good from bad we can train a neural network to sort out the topology for us. Eventually their RL model hits an asymptote, so they end up squeezing a bit more juice out of their approach by doing the same sampling procedure lined out above. So at the end of the day, Deepseek was less about RL and more about generating a lot of really high quality reasoning traces in a way that is less expensive than having humans do it by hand.

Get the Android app